© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5581
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list literal start

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,↵
    -0.03
    ,
    -0.02
    ][
    -0.02
    _result
    -0.02
    :-
    -0.02
    itude
    -0.02
    ache
    -0.01
    anage
    -0.01
    loor
    -0.01
    resh
    -0.01
    POSITIVE LOGITS
    urrent
    0.05
    [current
    0.04
    (current
    0.04
    cur
    0.04
     current
    0.03
    current
    0.03
    (start
    0.03
    form
    0.03
    .current
    0.03
    [start
    0.03
    Activations Density 58.082%

    No Known Activations